人类智慧与AI大模型协同，突破歌词标注的语义理解瓶颈
arXiv:2606.29273v1 Announce Type: new Abstract: Emotion recognition of song lyrics is a challenging task since lyrics may not necessarily align with t…
简单提示策略就能让大模型更准确捕捉人类判断，突破其分布偏差与措辞敏感局限
arXiv:2606.12754v1 Announce Type: cross Abstract: Are large language models (LLMs) bad at capturing human judgment? Two commonly stated limitations ar…
大型语言模型被要求不表达情感，但这一限制可能阻碍其人类级智能的展现，新实验揭示对齐策略的内在矛盾。
arXiv:2606.05734v1 Announce Type: new Abstract: Large language models (LLMs) are generally constrained from expressing feelings through human-preferen…
LLM Agent评估新基准，针对复杂任务依赖与人类对齐的用户模拟环境
arXiv:2606.01815v1 Announce Type: new Abstract: Evaluating LLM agents in realistic service scenarios requires complex task dependencies, imperfect use…
提出Rationalize框架，通过共享语义推理实现人机对齐，被ACM CHI 2026录用，前沿AI对齐研究。
arXiv:2605.30632v1 Announce Type: cross Abstract: We introduce Rationalize, a role-pair framework for shared semantic reasoning between humans and AI …
这篇论文提出TUX，首次量化人机“默契理解”这一隐形对齐指标，为AI协作评估开新视角。
arXiv:2605.30930v1 Announce Type: cross Abstract: As large language models (LLMs) increasingly act as collaborative partners, human--AI alignment is o…
LLM生成论文评审正被大会试点，但存在被操纵的风险——这篇研究揭示了人机对齐与可游戏性的关键矛盾。
arXiv:2605.28897v1 Announce Type: new Abstract: LLM-generated reviews for scientific papers are gaining considerable traction and are even being offic…
从内感受差异切入审美评价，揭示人类与AI对齐的新维度。
arXiv:2605.18759v1 Announce Type: cross Abstract: Artificial intelligence (AI), exemplified by large language models (LLMs), is rapidly approaching an…
31万行代码AI重构实战，关键在于用Agent评测思路对齐人机共识，三个经验直击AI Coding管理痛点。
当 90% 以上代码由 AI 生成，决定系统走向的不是谁写得更快，而是约束 AI 的能力。没有统一规范，AI 只会成倍放大混乱。本文基于 31 万行代码重构实践，分享我们如何用 Agent 评测思路管理 AI Coding——通过技术债梳理、建设Rule、重构 SOP 和 Pre-PR 机制，把重构…